{"id":"W7086854890","doi":"10.13130/rd_unimi/wiud6w","title":"Replication data for: “TAP-COG: Development and Preliminary Usability Evaluation of a New Tablet-Based Assessment of Cognitive Skills”","year":2025,"lang":"en","type":"dataset","venue":"","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Usability; Cognition; Replication (statistics); Cognitive walkthrough; Web usability; System usability scale; Usability engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003820091,0.0002666094,0.0005287936,0.0001787919,0.00007477243,0.00001567268,0.0004200488,0.0002360898,0.0009632102],"category_scores_gemma":[0.008503891,0.0002608901,0.00005667675,0.0002099546,0.0001470069,0.00008200866,0.0004283114,0.0001815589,9.226322e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001186156,"about_ca_system_score_gemma":0.002225808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001217588,"about_ca_topic_score_gemma":0.0003729837,"domain_scores_codex":[0.9968641,0.0003426168,0.000933902,0.001158699,0.0004830682,0.0002176537],"domain_scores_gemma":[0.9913289,0.004418082,0.0006834555,0.002210218,0.001295366,0.00006401046],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001771944,0.001116542,0.001611647,0.0009402047,0.000315863,3.188406e-7,0.0001442447,0.000002455347,0.000003301509,0.00007702335,0.8111756,0.1844356],"study_design_scores_gemma":[0.01376033,0.002513673,0.3260659,0.004361973,0.008978553,0.0000101685,0.004603833,0.006428473,0.0007483713,0.001516245,0.6295391,0.001473386],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.006216035,0.0003064318,0.005470169,0.00007596856,0.0001933944,0.003673106,0.9825361,0.00001799596,0.001510813],"genre_scores_gemma":[0.01173539,0.000008342303,0.006874678,0.0001081082,0.00004502049,0.0008443859,0.9800848,0.000009442877,0.0002898638],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.3244542,"threshold_uncertainty_score":0.9999843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1446206454505799,"score_gpt":0.4617326938617363,"score_spread":0.3171120484111564,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}